© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4378
    Prev
    Next
    INDEX
    Explanations

    phrases related to the presence and quantity of items or elements within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Minimum quantity or threshold

    np_acts-logits-general · gemini-2.0-flash

    at least one or more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.49
    Everything
    -0.49
     transfieras
    -0.48
     Everything
    -0.47
     GetEnumerator
    -0.45
     JAXBElement
    -0.44
    AsStream
    -0.43
    obel
    -0.42
     Sheppard
    -0.41
    чее
    -0.41
    POSITIVE LOGITS
     almeno
    1.55
     atleast
    1.51
    至少
    1.38
     mindestens
    1.37
     setidaknya
    1.19
    少なくとも
    1.18
     حداقل
    1.08
     wenigstens
    1.05
     минимум
    0.95
     multiple
    0.95
    Activations Density 0.688%

    No Known Activations